Grounding is crucial for natural language understanding. An important subtask is to understand modified color expressions, such as 'dirty blue'. We present a model of color modifiers that, compared with previous additive models in RGB space, learns more complex transformations. In addition, we present a model that operates in the HSV color space. We show that certain adjectives are better modeled in that space. To account for all modifiers, we train a hard ensemble model that selects a color space depending on the modifier color pair. Experimental results show significant and consistent improvements compared to the state-of-the-art baseline model.
@article{arxiv.1909.07586,
title = {Grounding learning of modifier dynamics: An application to color naming},
author = {Xudong Han and Philip Schulz and Trevor Cohn},
journal= {arXiv preprint arXiv:1909.07586},
year = {2019}
}